claude-homelab: Instructions file for Claude Code

CLAUDE.md

claude-homelab CLAUDE.md is an instructions file for Claude Code from jmagar/claude-homelab. It costs 6,382 tokens per session, scanned A, original, MIT.

Repository instructions for a Claude Code project that manages self-hosted homelab services. They explain the project’s skills, agents, commands, scripts, references, credentials, and repository layout.

In plain words
What is it for?
Use them when developing or maintaining homelab service integrations, adding commands or skills, working with service APIs, handling setup files, or troubleshooting the repository.
Why use it?
They give a coding agent the background needed to change this repository safely and consistently. They also clarify how local integrations are installed and where sensitive configuration belongs.

Instructions file for Claude Code

Written for Claude Code: $ARGUMENTS substitution. Also seen: reads .claude/ paths; mentions CLAUDE.md; names the TodoWrite tool.

This is jmagar/claude-homelab's own configuration. It tells Claude Code how to work on claude-homelab itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything claude-homelab configures →

Reuse

Borrowing it

Nothing to install: this file belongs to jmagar/claude-homelab. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/jmagar/claude-homelab/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/jmagar/claude-homelab

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for claude-homelab CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/jmagar/claude-homelab/claude-md/github.svg)](https://agentmods.dev/instructions/jmagar/claude-homelab/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/jmagar/claude-homelab/claude-md"><img src="https://agentmods.dev/badge/instructions/jmagar/claude-homelab/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for claude-homelab CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/jmagar/claude-homelab/claude-md"><img src="https://agentmods.dev/badge/instructions/jmagar/claude-homelab/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 6,382 This file is loaded in full into every session.
When invoked 6,382 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. ✓ AI security review Sonnet 5 · 7 Sept 2026 📄 Read the review
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.06382 $0.06382
Opus 5 $0.03191 $0.03191
Sonnet 5 $0.01276 $0.01276
Haiku 4.5 $0.00638 $0.00638

Measured 10d ago against content hash d383dddd07fe, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

claude-homelab CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

CLAUDE.md · 691 lines

How it starts

The opening of the file, as written. The whole thing — 691 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Claude Homelab - Development Guidelines

Comprehensive Claude Code skills, agents, and commands for homelab service management.

Glossary

  • Skill: A Claude Code plugin providing commands and scripts for a specific service (e.g., Plex, Radarr)
  • Agent: A specialized AI agent for complex workflows (e.g., notebooklm-specialist)
  • Command: A slash command invocable in Claude Code (e.g., /firecrawl:scrape, /homelab:docker-health)
  • Script: Executable code in skill scripts/ directories that performs API calls or system operations
  • Reference: Detailed documentation in skill references/ directories (API endpoints, troubleshooting, etc.)
  • Symlink: Symbolic link connecting this repo to ~/.claude/ for Claude Code discovery
  • SKILL.md: Claude-facing skill definition with commands, workflows, and examples
  • README.md: User-facing documentation for setting up and using a skill
  • .env: Environment file containing credentials (gitignored, NEVER commit)
  • .env.example: Template credential file (tracked in git, NO secrets)

Repository Overview

This repository provides production-ready integrations for self-hosted homelab services via a dual-path install:

  • Plugin path (/plugin marketplace add jmagar/claude-homelab) — Claude Code native plugin system

  • Bash path (curl -sSL .../install.sh | bash) — symlinks into ~/.claude/

  • homelab-core plugin — agents, commands, prompts, setup wizard, health dashboard (repo root IS the plugin)

  • Service skills (skills/) — 16 service integrations + 2 homelab-core skills (18 total); each skill directory is independently usable

  • Shared library (scripts/load-env.sh) — credential loading, installed to ~/.claude-homelab/

Repository Structure

claude-homelab/
├── README.md                        # User-facing documentation (comprehensive)
├── CLAUDE.md                        # This file - development guidelines
├── .env.example                     # Credential template (tracked, no secrets)
├── .claude-plugin/
│   ├── marketplace.json             # Plugin catalog (27 plugins)
│   └── plugin.json                  # homelab-core manifest (root IS the plugin)
│
├── agents/                          # homelab-core agents
│   └── notebooklm-specialist.md
│
├── commands/                        # homelab-core slash commands (.md definitions)
│   ├── check.md                     # /check
│   ├── deploy.md                    # /deploy
│   ├── quick-push.md                # /quick-push
│   ├── save-to-md.md                # /save-to-md
│   ├── validate-plan.md             # /validate-plan
│   ├── homelab/                     # /homelab:system-resources, docker-health, disk-space, zfs-health
│   └── notebooklm/                  # /notebooklm:create, ask, source, generate, download, list, research
│
├── prompts/                         # Command prompt definitions (.toml sidecars)
│   ├── check.toml                   # Prompt body for /check
│   ├── deploy.toml                  # Prompt body for /deploy
│   ├── quick-push.toml              # Prompt body for /quick-push
│   ├── save-to-md.toml              # Prompt body for /save-to-md
│   ├── validate-plan.toml           # Prompt body for /validate-plan
│   └── homelab/                     # Prompt bodies for /homelab:* commands
│       ├── disk-space.toml
│       ├── docker-health.toml
│       ├── system-resources.toml
│       └── zfs-health.toml
│
├── docs/references/                 # Shared reference documentation
│   └── security-patterns.md         # Reusable security patterns for scripts
│
├── skills/                          # All service skills (16 services + 2 homelab-core)
│   ├── CLAUDE.md                    # Skill development guidelines
│   ├── homelab-setup/SKILL.md       # /homelab-core:setup — interactive credential wizard
│   ├── homelab-health/
│   │   ├── SKILL.md                 # /homelab-core:health — service health dashboard
│   │   └── scripts/check-health.sh  # Curl-checks all services, outputs JSON
│   └── [service]/                   # e.g., plex/, radarr/, sonarr/, ...
│       ├── SKILL.md                 # Skill definition
│       ├── scripts/                 # Bash/Python/Node API scripts
│       └── references/              # API docs, quick-reference, troubleshooting
│
└── scripts/                         # Install and maintenance scripts
    ├── install.sh                   # Bash path entry point
    ├── setup-creds.sh               # Creates ~/.claude-homelab/.env (both paths)
    ├── setup-symlinks.sh            # Bash path: symlinks skills/ → ~/.claude/skills/
    └── verify.sh                    # Dual-path verification (exits 0 if clean)

Read the full file on GitHub · 691 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 10d ago First seen · 691 lines · 6,382 tokens per session scan E d383dddd07fe

Subscribe to this mod's changes

claude-homelab CLAUDE.md is an instructions file published in the GitHub repository jmagar/claude-homelab (78 stars, last pushed 1mo ago), licensed MIT. It adds 6,382 tokens to every session, about $0.0319 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other instructions, from other repositories

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens